Intel’s Server and PC Chip Development Will Blur After 2025

By Agam Shah

January 15, 2024

Intel’s dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificial intelligence, and a tight roadmap of manufacturing advances.

To its advantage, Intel is the only fully integrated chip company that can offer chips or manufacturing services to companies that design their own chips. One of the two should stick; if rivals Nvidia, ARM, AMD, Qualcomm, and Apple take market share from Intel, the chip maker still wants to get business to manufacture those chips.

At last month’s Meteor Lake chip launch event in New York City, Intel’s Pat Gelsinger shared a little more on how the company is thinking when designing chips and timelines after it achieves its goal of retaining manufacturing leadership by next year.

Intel is currently on the path to integrating five new nodes in four years, which should culminate in 2025. The first node was Intel 7, which is behind the Emerald Rapids server chips. The Meteor Lake chip, also announced last month, is shipping on the Intel 4 process.

Intel 18A process wafer held by Pat Gelsinger, Intel CEO

Server chips Granite Rapids and Sierra Forest come this year on Intel 3, while a chip code-named Arrow Lake – the successor to Meteor Lake — will also be released this year on the Intel 20A process. Intel has shown samples of the 20A chips in action, indicating the manufacturing process is evolving rapidly.

The last is the Intel 18A process, which will be used for the Clearwater Forest, which is the successor to Sierra Forest. The chips are for dense servers with Intel e-core designs, which are designed for more efficient processing.

Beyond that, nobody knows. At this point, Intel has thrown away its typical cadence to release chips and shipping products when ready. Intel just wants to catch up with rivals on both chips and manufacturing and believes that selling multiple generations of chips simultaneously provides more options to customers.

The timed releases of server and PC ships could take a backseat as customized chips will be in vogue beyond 2025, said Pat Gelsinger, Intel CEO, in response to a question from HPCwire in a press conference.

Chiplet technologies will blur the lines between server products and client products, and chip making will be a matter of patching together the right parts based on what clients want, Gelsinger said.

Intel could fancy up piece together custom chips targeted directly at verticals and do it quickly, Gelsinger said.

He gave some examples of patching together AI or telecom accelerator chips where it can slap on chiplets that do security and other functions and not worry about making a monolithic chip.

Intel’s disaggregated chip design approach is evident with the Falcon Shores supercomputing chips, which has seen many iterations. The original Falcon Shore chip was conceived as an integrated CPU-GPU chip, much like the MI300 chip from AMD. But Intel’s now releasing Falcon Shores as a separate GPU, with the flexibility to attach CPUs to it.

“I think this was a pivot that we made in large part to ChatGPT and just the shift and how the market was going. And so looking at the assets that we had, we wanted to make sure that we took advantage of both,” said Radhika Rao, senior director of data center GPU product management at Intel, in an interview with HPCwire at last year’s Supercomputing 2023 show.

Innovations can get faster with the ability to customize and put all kinds of chiplets in a single package, Gelsinger said.

“As you go to chiplets, you’re not doing as large a die, and you have smaller die. In fact, when we go to 18A, a finish of our five nodes in four years, we’re almost concurrently taping out the client and server parts. That’s something we’ve never done before,” Gelsinger said.

Cloud providers are demanding more custom chips to meet customer demand. Intel can offer a giant menu of features that it can package into chips, which can then be manufactured for the chip provider.

To be sure, chiplets aren’t new. AMD has been using chiplet designs with TSMC’s packaging technology for years, and Apple makes fast PC chips with deep integration of memory and I/O in its M-series chips for Macs.

Gelsinger was speaking at a press conference held at the launch event for its Meteor Lake chip, Core Ultra, the first commercial PC chip with chiplet design. The chip has AI, security, graphics, and CPU chiplets in one package. Unfortunately, the initial reviews show Intel has gone for power efficiency over performance, and in most cases, the performance and power efficiency fell short of Apple’s latest M-series chips and, in some cases, AMD’s PC chips.

“We look at the Core Ultra packaging — we’re innovating on Foveros packaging, but we’re going to be using that on the next generation server part in this chiplet architecture, there are so many ways to blur the lines between many of our designs,” Gelsinger said.

The Granite Rapids and Sierra Forest chips will also made with Foveros packaging.

“Some of the AI tools do make us a lot faster. All of this will be formally verified before we even send the first silicon into the fab,” Gelsinger said.

Intel’s go-to-market will be vertical because the SOCs will ultimately be industry-focused.

“Disaggregation allows us to have a lot of flexibility,” said Sandra Rivera, executive vice president of Intel and CEO of the Programmable Solutions Group, which was spun off into an independent entity within the organization.

Chips can integrate tiles from the latest process node into the base die, which can be used with tiles such as I/O from older process nodes. That can bring chips “to market much more quickly, much more cost-effectively,” Rivera said.

Older monolithic chips were all made on a single process node. Chiplets allow 3-nanometer chips to be paired with chips from older nodes, such as power management chips on 28-nanometer. Many analog chips don’t scale well to the latest process nodes and are more cost-effective when made on older ones. Performance-based chips such as CPUs and GPUs typically use the latest process nodes.

Moving away from concurrent design to a more fluid design philosophy will become clearer once Intel moves beyond the Clearwater Forest chip on 18A, known as the Angstrom era. Intel has indicated it will reach 18A on time.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Can Cerabyte Crack the $1-Per-Petabyte Barrier with Ceramic Storage?

July 20, 2024

A German startup named Cerabyte is hoping to solve the burgeoning market for secondary and archival data storage with a novel approach that uses lasers to etch bits onto glass with a ceramic coating. The “grey ceramic� Read more…

Weekly Wire Roundup: July 15-July 19, 2024

July 19, 2024

It's summertime (for most of us), and the HPC-related headlines aren't as plentiful as they once were. But not everything has to happen at high tide-- this week still had some waves! Idaho National Laboratory's Bitter Read more…

ARM, Fujitsu Targeting Open-source Software for Power Efficiency in 2-nm Chip

July 19, 2024

Fujitsu and ARM are relying on open-source software to bring power efficiency to an air-cooled supercomputing chip that will ship in 2027. Monaka chip, which will be made using the 2-nanometer process, is based on the Read more…

SCALEing the CUDA Castle

July 18, 2024

In a previous article, HPCwire has reported on a way in which AMD can get across the CUDA moat that protects the Nvidia CUDA castle (at least for PyTorch AI projects.). Other tools have joined the CUDA castle siege. AMD Read more…

Quantum Watchers – Terrific Interview with Caltech’s John Preskill by CERN

July 17, 2024

In case you missed it, there's a fascinating interview with John Preskill, the prominent Caltech physicist and pioneering quantum computing researcher that was recently posted by CERN’s department of experimental physi Read more…

Aurora AI-Driven Atmosphere Model is 5,000x Faster Than Traditional Systems

July 16, 2024

While the onset of human-driven climate change brings with it many horrors, the increase in the frequency and strength of storms poses an enormous threat to communities across the globe. As climate change is warming ocea Read more…

Can Cerabyte Crack the $1-Per-Petabyte Barrier with Ceramic Storage?

July 20, 2024

A German startup named Cerabyte is hoping to solve the burgeoning market for secondary and archival data storage with a novel approach that uses lasers to etch Read more…

SCALEing the CUDA Castle

July 18, 2024

In a previous article, HPCwire has reported on a way in which AMD can get across the CUDA moat that protects the Nvidia CUDA castle (at least for PyTorch AI pro Read more…

Aurora AI-Driven Atmosphere Model is 5,000x Faster Than Traditional Systems

July 16, 2024

While the onset of human-driven climate change brings with it many horrors, the increase in the frequency and strength of storms poses an enormous threat to com Read more…

Shutterstock 1886124835

Researchers Say Memory Bandwidth and NVLink Speeds in Hopper Not So Simple

July 15, 2024

Researchers measured the real-world bandwidth of Nvidia's Grace Hopper superchip, with the chip-to-chip interconnect results falling well short of theoretical c Read more…

Shutterstock 2203611339

NSF Issues Next Solicitation and More Detail on National Quantum Virtual Laboratory

July 10, 2024

After percolating for roughly a year, NSF has issued the next solicitation for the National Quantum Virtual Lab program — this one focused on design and imple Read more…

NCSA’s SEAS Team Keeps APACE of AlphaFold2

July 9, 2024

High-performance computing (HPC) can often be challenging for researchers to use because it requires expertise in working with large datasets, scaling the softw Read more…

Anders Jensen on Europe’s Plan for AI-optimized Supercomputers, Welcoming the UK, and More

July 8, 2024

The recent ISC24 conference in Hamburg showcased LUMI and other leadership-class supercomputers co-funded by the EuroHPC Joint Undertaking (JU), including three Read more…

Generative AI to Account for 1.5% of World’s Power Consumption by 2029

July 8, 2024

Generative AI will take on a larger chunk of the world's power consumption to keep up with the hefty hardware requirements to run applications. "AI chips repres Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Everyone Except Nvidia Forms Ultra Accelerator Link (UALink) Consortium

May 30, 2024

Consider the GPU. An island of SIMD greatness that makes light work of matrix math. Originally designed to rapidly paint dots on a computer monitor, it was then Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…


Nvidia Economics: Make $5-$7 for Every $1 Spent on GPUs

June 30, 2024

Nvidia is saying that companies could make $5 to $7 for every $1 invested in GPUs over a four-year period. Customers are investing billions in new Nvidia hardwa Read more…

Nvidia Shipped 3.76 Million Data-center GPUs in 2023, According to Study

June 10, 2024

Nvidia had an explosive 2023 in data-center GPU shipments, which totaled roughly 3.76 million units, according to a study conducted by semiconductor analyst fir Read more…

AMD Clears Up Messy GPU Roadmap, Upgrades Chips Annually

June 3, 2024

In the world of AI, there's a desperate search for an alternative to Nvidia's GPUs, and AMD is stepping up to the plate. AMD detailed its updated GPU roadmap, w Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

Intel’s Next-gen Falcon Shores Coming Out in Late 2025 

April 30, 2024

It's a long wait for customers hanging on for Intel's next-generation GPU, Falcon Shores, which will be released in late 2025.  "Then we have a rich, a very Read more…

Leading Solution Providers


Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l Read more…

IonQ Plots Path to Commercial (Quantum) Advantage

July 2, 2024

IonQ, the trapped ion quantum computing specialist, delivered a progress report last week firming up 2024/25 product goals and reviewing its technology roadmap. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

  • arrow
  • Click Here for More Headlines
  • arrow